* governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor;

import java.io.InputStream;
import java.util.Map;

import org.codelibs.fess.crawler.entity.ExtractData;

/**
 * The Extractor interface defines methods for extracting text data from an input stream.
 * Implementations of this interface should provide the logic for extracting text and

		class="org.codelibs.fess.crawler.extractor.impl.MsPowerPointExtractor" />
	<component name="msPublisherExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.MsPublisherExtractor" />
	<component name="msVisioExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.MsVisioExtractor" />
	<component name="pdfExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.PdfExtractor" />
	<component name="lhaExtractor"

	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">2</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.

        final CommandExtractor extractor = new CommandExtractor();
        extractor.executionTimeout = 1000L;
        extractor.command = getCommand(scriptFile);
        final Map<String, String> params = new HashMap<String, String>();
        try {
            final ExtractData data = extractor.getText(new FileInputStream(contentFile), params);
            fail(data.toString());

            throw new FessSystemException("Could not find extractorFactory.");
        }
        final Extractor extractor = extractorFactory.getExtractor(responseData.getMimeType());
        if (logger.isDebugEnabled()) {
            logger.debug("url={}, extractor={}", responseData.getUrl(), extractor);
        }
        return extractor;
    }

        final AtomicBoolean streamClosed = new AtomicBoolean(false);

        try (final InputStream originalStream = ResourceUtil.getResourceAsStream("extractor/msoffice/test.xls")) {
            final InputStream trackableStream = createTrackableInputStream(originalStream, streamClosed);
            final ExtractData result = extractor.getText(trackableStream, null);

    // InputStream in =
    // ResourceUtil.getResourceAsStream("extractor/test_pass.pdf");
    // TikaExtractor extractor =
    // (TikaExtractor) getContainer().getComponent(
    // "tikaExtractorForPdfPassword");
    // Map<String, String> params = new HashMap<String, String>();
    // params.put(ExtractData.URL, "http://example.com/test_pass.pdf");
    // ExtractData extractData = extractor.getText(in, params);

    private TestApiExtractorServer server;

    private ApiExtractor extractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

        server = new TestApiExtractorServer(port);
        server.start();

        extractor = new ApiExtractor();
        extractor.setUrl("http://127.0.0.1:" + port + "/");
        extractor.init();
    }

    @Override

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;